search

MLJejuCamp2017 / DRL_based_SelfDrivingCarControl

Deep Reinforcement Learning (DQN) based Self Driving Car Control with Vehicle Simulator
293 stars 95 forks source link

About training #19

Closed Malathi15 closed 4 years ago

Malathi15 commented 4 years ago

Hi @Kyushik , I'm using Ubuntu 16.04. I have run the file Double_Dueling_image.ipynb. The Num_training = 1000000 is done but still the training is not stopped.

When will the training stop or how can I stop the training?

Thanks in Advance

Kyushik commented 4 years ago

Hi! :) Training is finished when step is Num_start_training + Num_training. So, if Num_start_training = 50000 and Num_training = 1000000, training is finished at step == 1050000.

Malathi15 commented 4 years ago

@Kyushik Thanks for your reply :)

How is the distance calculated in Double_Dueling_image.ipynb? Is that using sensor?

Kyushik commented 4 years ago

Yes. That is the distance which is provided by the sensor. I obtain the value using raycast in Unity.